Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDialogue Response Generation via Contrastive Latent Representation Learning
جيل استجابة الحوار عن طريق التعلم التمثيل الكامن النقيض
323
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
حققت النماذج التراجعية التلقائية واسعة النطاق نجاحا كبيرا في توليد استجابة الحوار، بمساعدة طبقات المحولات. ومع ذلك، فإن هذه النماذج لا تتعلم مساحة كامنة تمثيلية لتوزيع الجملة، مما يجعل من الصعب التحكم في الجيل. لقد حاولت الأعمال الحديثة على تعلم تمثيلات الجملة باستخدام الإطار القائم على المحولات، ولكن لا تطلق على علاقة استجابة السياق المضمنة في مجموعات بيانات الحوار. في هذا العمل، نهدف إلى إنشاء نموذج لتعليم التمثيل القوي التمثيل، وهو مصمم خصيصا لتوليد استجابة الحوار، مع هيكل ترميز الترميز المستندة إلى المحولات. يقترح التعلم المتعرج عن مستوى الكلام، وترميز المعلومات التنبؤية في كل تمثيل سياق لاستجابة لها المقابلة. يتم إجراء تجارب واسعة للتحقق من تقلب آلية تعليم التمثيل المقترح. باستخدام كلا من مقاييس التقييم المستندة إلى المرجعية والمرجعية، نقدم تحليلا مفصلا على الجمل التي تم إنشاؤها، مما يدل على فعالية نموذجنا المقترح.
Large-scale auto-regressive models have achieved great success in dialogue response generation, with the help of Transformer layers. However, these models do not learn a representative latent space of the sentence distribution, making it hard to control the generation. Recent works have tried on learning sentence representations using Transformer-based framework, but do not model the context-response relationship embedded in the dialogue datasets. In this work, we aim to construct a robust sentence representation learning model, that is specifically designed for dialogue response generation, with Transformer-based encoder-decoder structure. An utterance-level contrastive learning is proposed, encoding predictive information in each context representation for its corresponding response. Extensive experiments are conducted to verify the robustness of the proposed representation learning mechanism. By using both reference-based and reference-free evaluation metrics, we provide detailed analysis on the generated sentences, demonstrating the effectiveness of our proposed model.
References used
https://aclanthology.org/
rate research
Read More
For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis
et al., 2020), a pre-trained transformer encoder-decoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method with the goal
of learning a better representation of the style and the content. This method is mainly motivated by the recent success of contrastive learning which has demonstrated its power in unsupervised feature extraction tasks. The idea is to design two contrastive losses with respect to the content and the style by considering two problem characteristics during training. One characteristic is that the target sentence shares the same content with the source sentence, and the second characteristic is that the target sentence shares the same style with the exemplar. These two contrastive losses are incorporated into the general encoder-decoder paradigm. Experiments on two datasets, namely QQP-Pos and ParaNMT, demonstrate the effectiveness of our proposed constrastive losses.
Humans use commonsense reasoning (CSR) implicitly to produce natural and coherent responses in conversations. Aiming to close the gap between current response generation (RG) models and human communication abilities, we want to understand why RG mode
ls respond as they do by probing RG model's understanding of commonsense reasoning that elicits proper responses. We formalize the problem by framing commonsense as a latent variable in the RG task and using explanations for responses as textual form of commonsense. We collect 6k annotated explanations justifying responses from four dialogue datasets and ask humans to verify them and propose two probing settings to evaluate RG models' CSR capabilities. Probing results show that models fail to capture the logical relations between commonsense explanations and responses and fine-tuning on in-domain data and increasing model sizes do not lead to understanding of CSR for RG. We hope our study motivates more research in making RG models emulate the human reasoning process in pursuit of smooth human-AI communication.
Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-network for this task, which obtains the sentence embeddings through mo
deling the context-response semantic relevance by applying a feed-forward network on top of the sentence encoders. However, as the semantic textual similarity is commonly measured through the element-wise distance metrics (e.g. cosine and L2 distance), such architecture yields a large gap between training and evaluating. In this paper, we propose DialogueCSE, a dialogue-based contrastive learning approach to tackle this issue. DialogueCSE first introduces a novel matching-guided embedding (MGE) mechanism, which generates a context-aware embedding for each candidate response embedding (i.e. the context-free embedding) according to the guidance of the multi-turn context-response matching matrices. Then it pairs each context-aware embedding with its corresponding context-free embedding and finally minimizes the contrastive loss across all pairs. We evaluate our model on three multi-turn dialogue datasets: the Microsoft Dialogue Corpus, the Jing Dong Dialogue Corpus, and the E-commerce Dialogue Corpus. Evaluation results show that our approach significantly outperforms the baselines across all three datasets in terms of MAP and Spearman's correlation measures, demonstrating its effectiveness. Further quantitative experiments show that our approach achieves better performance when leveraging more dialogue context and remains robust when less training data is provided.
In open-domain dialogue response generation, a dialogue context can be continued with diverse responses, and the dialogue models should capture such one-to-many relations. In this work, we first analyze the training objective of dialogue models from
the view of Kullback-Leibler divergence (KLD) and show that the gap between the real world probability distribution and the single-referenced data's probability distribution prevents the model from learning the one-to-many relations efficiently. Then we explore approaches to multi-referenced training in two aspects. Data-wise, we generate diverse pseudo references from a powerful pretrained model to build multi-referenced data that provides a better approximation of the real-world distribution. Model-wise, we propose to equip variational models with an expressive prior, named linear Gaussian model (LGM). Experimental results of automated evaluation and human evaluation show that the methods yield significant improvements over baselines.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
